diff --git a/src/main.py b/src/main.py
index 243a31e..eabde6f 100644
--- a/src/main.py
+++ b/src/main.py
@@ -1,20 +1,25 @@
-from PIL import Image
+import logging
+
+import numpy as np
 import torch
 import torch.nn as nn
 import torch.optim as optim
-from torchvision import datasets, transforms
 from torch.utils.data import DataLoader
-import numpy as np
+from torchvision import datasets, transforms
+
+logging.basicConfig(
+    filename="training.log", level=logging.INFO, format="%(asctime)s %(message)s"
+)
 
 # Step 1: Load MNIST Data and Preprocess
-transform = transforms.Compose([
-    transforms.ToTensor(),
-    transforms.Normalize((0.5,), (0.5,))
-])
+transform = transforms.Compose(
+    [transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]
+)
 
-trainset = datasets.MNIST('.', download=True, train=True, transform=transform)
+trainset = datasets.MNIST(".", download=True, train=True, transform=transform)
 trainloader = DataLoader(trainset, batch_size=64, shuffle=True)
 
+
 # Step 2: Define the PyTorch Model
 class Net(nn.Module):
     def __init__(self):
@@ -22,7 +27,7 @@ def __init__(self):
         self.fc1 = nn.Linear(28 * 28, 128)
         self.fc2 = nn.Linear(128, 64)
         self.fc3 = nn.Linear(64, 10)
-    
+
     def forward(self, x):
         x = x.view(-1, 28 * 28)
         x = nn.functional.relu(self.fc1(x))
@@ -30,6 +35,7 @@ def forward(self, x):
         x = self.fc3(x)
         return nn.functional.log_softmax(x, dim=1)
 
+
 # Step 3: Train the Model
 model = Net()
 optimizer = optim.SGD(model.parameters(), lr=0.01)
@@ -42,7 +48,8 @@ def forward(self, x):
         optimizer.zero_grad()
         output = model(images)
         loss = criterion(output, labels)
+        logging.info("Epoch: %s, Loss: %s", epoch, loss.item())
         loss.backward()
         optimizer.step()
 
-torch.save(model.state_dict(), "mnist_model.pth")
\ No newline at end of file
+torch.save(model.state_dict(), "mnist_model.pth")